Koios Decision Support (DS) for Breast is a software application designed to assist trained interpreting physicians in analyzing the breast ultrasound images of patients with soft tissue breast lesions who are being referred for further diagnostic ultrasound examination. Koios DS for Breast is a machine learning-based decision support system, indicated as an adjunct to diagnostic ultrasound for breast cancer. Koios DS for Breast automatically classifies user-selected region(s) of interest (ROIs) containing a breast lesion into four BI-RADS-aligned categories (Benign, Suspicious, Probably Malignant), and displays a continuous graphical confidence level indicator of where the lesson falls across all categories. Koios DS for Breast also automatically classifies lesion shape and orientation according to BI-RADS descriptors.

The software requires a user to select up to two orthogonal views, that represent a single lesion to be selected and processed. When utilized by an interpreting physician who has completed training, this device provides information that may be useful in rendering an accurate diagnosis. Patient management decisions should not be made solely on the results of the Koios DS for Breast analysis. This device is intended to help trained interpreting physicians improve their overall accuracy as well as reduce inter- and intra-operator variability.

Koios DS for Breast may also be used as an image viewer of multi-modality digital images, including ultrasound and mammography. The software includes tools that allow users to adjust, measure and document images, and output into a structured report.

Limitations: Koios DS for Breast is not to be used on sites of post-surgical excision, or images with doppler, elastography, or other overlays present in them. Koios DS for Breast is not intended for the primary interpretation of digital mammography images. Koios DS for Breast is not intended for use on mobile devices.

Device Description

Koios Decision Support (DS) for Breast is a software application designed to assist trained interpreting physicians in analyzing breast ultrasound images. The system provides image derived data via web triggering and remote analysis. The software device is a web application that is deployed to a Microsoft IIS web server and accessed by a user through a compatible client. Once logged in and granted access to the Koios DS for Breast application, the user examines selected breast ultrasound DICOM images. The user selects up to two Regions of Interest (ROIs) of two orthogonal views of a breast lesion for processing by Koios DS for Breast. The ROI(s) are transmitted electronically to the Koios DS for Breast server for image processing and the results are returned to the user for review.

The Koios DS for Breast core engine characterizes image features using the ROI data to generate a categorical output that aligns to BI-RADS categories. The engine uses computer vision and machine learning techniques embedded within a software capable of reading, interpreting, analyzing, and generating findings from ultrasound data. The underlying engine draws upon knowledge learned from a large database of known cases, tying image features to their eventual diagnosis, to form a predictive model. The categorical output of the Koios DS for Breast engine is divided into four categories (Benign, Probably Benign, Suspicious, Probably Malignant), separated by three operating points, aligning with or exceeding the sensitivity and specificity of radiologist chosen BI-RADS categorizations. . The output of the system is a digital display to be used as a concurrent read. Koios DS for Breast is intended to support compliance with the ACR BI-RADS ultrasound lexicon classification form. The engine additionally classifies the region of interest on the basis of shape (Oval, Round, Irregular) and orientation (Parallel to Skin, Not Parallel).

Koios DS for Breast results can be saved or transferred in three separate ways: in-transit transmission, PACS saving, and exporting results to third-party reporting software. Intransit transmission may be utilized when users wish to share analyses across viewing workstations. Results can be stored in in-transit memory for a preset period of time defined by a system administrator. These results are never locally cached, written to disk, or otherwise stored outside of in-transit memory. After that preset period of time, all results are wiped from the local memory.

Another method of saving is storing a report in the patient series on the PACS. After single or multiple breast lesion analyses have been performed and ultimately accepted by a trained interpreting physician, Koios DS for Breast can export a summary report to PACS as an addendum to the DICOM series that was selected for processing. This report serves as future reference and aid in comparison of cases requiring follow up. This functionality is strictly reserved for approved users.

Koios DS for Breast also supports exporting results to third-party reporting software to facilitate the reporting process. Saving or exporting preferences can be configured by the system administrator and user.

The Koios DS for Breast software is an ASP.NET web application that is deployed to an IIS Web Server inside a Windows operating system environment. The software does not require any specialized hardware, but the time to process ROIs will vary depending on the hardware specifications. If utilizing the recommended technical specifications, the time to generate and present results for two analyzed ROIs will be <= 2 seconds. The Koios DS for Breast processing software is a platform agnostic web service that queries and accepts DICOM compliant digital medical files from any DICOM compliant device.

Koios DS for Breast is intended to be used on patients with soft tissue breast lesions who are being referred for further diagnostic ultrasound examination.

AI/ML Overview

Here's a breakdown of the acceptance criteria and the study proving the device's performance, based on the provided FDA 510(k) summary for Koios DS for Breast:

Table of Acceptance Criteria and Reported Device Performance

Performance Metric	Acceptance Criteria	Reported Device Performance	Conclusion
MRMC Study (AUC Shift)	Statistically significant increase in AUC (Quantitative - implied by comparison to predicate and similar success criteria)	Mean AUC shift of +0.037 (95% CI: 0.030, 0.044) at α = 0.05	Satisfied (Primary Endpoint)
Inter-operator Variability (Kendall Tau-B)	Statistically significant increase in Kendall Tau-B (implied by demonstrating an improvement over USE Alone)	Average Kendall Tau-B increased from 0.5404 (USE Alone) to 0.6797 (USE + DS) (95% CI: 0.6653, 0.6941) with a significant increase demonstrated (α = 0.05)	Satisfied
Intra-operator Variability (Class Switching Rate)	Statistically significant reduction in intra-reader variability (implied by demonstrating an improvement over USE Alone)	Class switching rate reduced from 13.6% (USE Alone) to 10.8% (USE + DS) (p = 0.042)	Satisfied
Standalone Performance (AUC)	Implying high AUC given the clinical context of a diagnostic aid	88.2% AUC	Achieved
BI-RADS Descriptors - Lesion Orientation (Accuracy)	Overall accuracy falls within the 95% confidence interval of radiologists' performance. (Specific numerical cut-off: 86.12%)	91.12% (95% CI: 89.43% - 92.60%)	Within criteria established for clinical equivalence
BI-RADS Descriptors - Lesion Shape (Accuracy)	Overall accuracy falls within the 95% confidence interval of radiologists' performance. (Specific numerical cut-off: 83.54%)	87.62% (95% CI: 85.68% - 89.36%)	Within criteria established for clinical equivalence
BI-RADS Descriptors - Shape (Cohen's Kappa)	No statistical difference between reader vs. reader agreement and system vs. reader agreement	0.769 (Reader vs Reader) vs. 0.738 (System vs Reader) (95% CI overlap)	Not statistically different
BI-RADS Descriptors - Orientation (Cohen's Kappa)	No statistical difference between reader vs. reader agreement and system vs. reader agreement	0.728 (Reader vs Reader) vs. 0.744 (System vs Reader) (95% CI overlap)	Not statistically different

Study Details

1. Sample Sizes for Test Sets and Data Provenance:

MRMC Clinical Study:
- Cases: 900 patient cases. Each case included up to two orthogonal views of a single breast lesion.
- Data Provenance: Not explicitly stated, but the demographic information for patients (race, age distribution, breast density) is presented in a way that suggests a diverse, likely multi-center, retrospective dataset representative of national rates (Breast Cancer Surveillance Consortium 2006-2009 reference). It is implied to be retrospective as patients "present with a soft tissue breast lesion who are being referred for further diagnostic ultrasound examination" and their ground truth determined by pathology or 1-year follow-up.
Standalone Performance (Malignancy Risk Classification):
- Cases: 900 lesions from 900 different patients. Each lesion represented by two orthogonal images (total 1800 images). This data was specifically "set aside from the system's training data" for validation.
- Data Provenance: Not explicitly stated, but implies similar provenance to the MRMC study's test set as it's a validation set from their overall data.
BI-RADS Descriptors Bench Testing (Shape and Orientation):
- Cases: 1300 cases.
- Data Provenance: Not explicitly stated.

2. Number of Experts Used to Establish Ground Truth for Test Sets and Qualifications:

MRMC Clinical Study: The ground truth for the 900 cases in the MRMC study was "determined by pathology or 1-year follow-up for cases that were not biopsied" (stated under "Malignancy Risk Classification" for the standalone test, but applies to the overall definition of malignancy/benignancy for the test set). No human experts were used to establish the ground truth for the malignancy outcome itself for either the MRMC study or standalone performance validation.
BI-RADS Descriptors Bench Testing (Shape and Orientation):
- Number of Experts: Three MQSA certified radiologists.
- Qualifications: All with over 20 years of experience and at least 3000 images read per year.

3. Adjudication Method for the Test Set:

MRMC Clinical Study & Standalone Malignancy: Ground truth was established by pathology or 1-year follow-up. This is an objective ground truth, so no adjudication among experts was needed for disease status.
BI-RADS Descriptors Bench Testing: Ground truth for shape and orientation was established by majority decision of the three radiologists. For the second test comparing agreement (Cohen's Kappa), "majority agreement was not enforced and all cases were analyzed for reader and reader-system agreement," implying individual assessments were used for pairwise comparisons.

4. If a Multi-Reader Multi-Case (MRMC) Comparative Effectiveness Study was done, and its effect size:

Yes, an MRMC comparative effectiveness study was done.
Study Objective: To determine the impact on Interpreting Physician (Reader) performance (measured by AUC) when Koios DS for Breast and an ultrasound examination are combined (USE + DS), compared to USE Alone.
Effect Size: The study showed a mean AUC shift of +0.037 (from 0.836 for USE Alone to 0.873 for USE + DS). This was found to be statistically significant.
Inter-reader Variability: The average Kendall Tau-B coefficient significantly increased from 0.5404 (USE Alone) to 0.6797 (USE + DS), indicating a reduction in inter-reader variability with AI assistance.
Intra-reader Variability: The class switching rate (a measure of intra-reader variability) was statistically significantly reduced from 13.6% (USE Alone) to 10.8% (USE + DS), demonstrating improvement.

5. If a Standalone (algorithm only without human-in-the-loop performance) was done:

Yes, standalone performance was evaluated for malignancy risk classification and BI-RADS descriptors.
- Malignancy Risk Classification (algorithm only): Achieved an AUC of 88.2% on a validation set of 900 lesions.
- BI-RADS Descriptors (algorithm only): The system's accuracy for shape (87.62%) and orientation (91.12%) classification was compared to and found to be statistically equivalent to human radiologists' performance based on majority decisions. The agreement (Cohen's Kappa) between the system and readers was also found to be not statistically different from agreement between pairs of readers.

6. Type of Ground Truth Used:

For Malignancy Risk Classification (both MRMC and standalone): Ground truth was determined objectively by pathology or 1-year clinical follow-up for cases not biopsied. This is a robust form of ground truth based on definitive outcomes.
For BI-RADS Descriptors (Shape and Orientation): Ground truth was established by expert consensus (majority decision) of three highly experienced, MQSA-certified radiologists.

7. Sample Size for Training Set:

The document states that the underlying engine "draws upon knowledge learned from a large database of known cases" but does not specify the exact sample size of the training set. It only mentions that the 900 cases for standalone validation were "set aside from the system's training data."

8. How Ground Truth for Training Set was Established:

The document states that the engine "draws upon knowledge learned from a large database of known cases, tying image features to their eventual diagnosis, to form a predictive model." While not explicitly detailed, this implies that the ground truth for training data was also established using definitive outcomes like pathology or clinical follow-up, similar to the validation set, to ensure accurate "known cases." For the BI-RADS descriptors, it's mentioned that Koios DS for Breast and cCAD (its predecessor) "share a similar algorithm set, training data, and validation approach for automated shape and orientation assessment," which generally suggests the use of expert annotations for these subjective descriptors.

Summary

{0}------------------------------------------------

Image /page/0/Picture/0 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). The logo consists of two parts: a symbol on the left and the text "FDA U.S. FOOD & DRUG ADMINISTRATION" on the right. The symbol on the left is a stylized image of a caduceus, which is a traditional symbol of medicine. The text on the right is in blue and is arranged in three lines.

July 3, 2019

Koios Medical, Inc. % Mr. Lev Barinov VP of Clinical Excellence and Applied Research 500 7th Avenue, 8th Floor NEW YORK NY 10018

Re: K190442

Trade/Device Name: Koios DS for Breast Regulation Number: 21 CFR 892.2060 Regulation Name: Computer-assisted diagnostic software for lesions suspicious for cancer Regulatory Class: Class II Product Code: POK Dated: June 27, 2019 Received: June 28, 2019

Dear Mr. Barinov:

We have reviewed your Section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database located at https://www.accessdata.fda.gov/scripts/cdrh/cfdocs/cfpmp/pmn.cfm identifies combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.

If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR 803) for devices or postmarketing safety reporting (21 CFR 4, Subpart B) for combination products (see

{1}------------------------------------------------

https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR 1000-1050.

Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR Part 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.

For comprehensive regulatory information about medical devices and radiation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).

Sincerely,

For

Thalia T. Mills, Ph.D. Director Division of Radiological Health OHT7: Office of In Vitro Diagnostics and Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health

Enclosure

{2}------------------------------------------------

Indications for Use

510(k) Number (if known) K190442

Device Name Koios DS for Breast

Indications for Use (Describe)

Type of Use (Select one or both, as applicable)
☑ Prescription Use (Part 21 CFR 801 Subpart D)	☐ Over-The-Counter Use (21 CFR 801 Subpart C)

CONTINUE ON A SEPARATE PAGE IF NEEDED.

This section applies only to requirements of the Paperwork Reduction Act of 1995.

DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.

The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:

Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff@fda.hhs.gov

"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."

{3}------------------------------------------------

5. 510(k) Summarv of Safety and Effectiveness

This 510(k) summary of safety and effectiveness information is submitted as part of the Pre-Market Notification in accordance with the requirements of 21 CFR Part 807. Subpart E and Section 807.92.

1. Identification of Submitter:

Submitter:	Koios Medical Inc.
Address:	500 7th Avenue8th FloorNew York, NY 10018
Phone:	732-529-5755
Fax:	732-529-5757
Contact:	Lev Barinov
Title:	VP of Clinical Excellence & Applied Research
Phone:	732-529-5755
Fax:	732-529-5757
Summary Date:	February 21, 2019

2. Identification of Product:

Device Name: Koios DS for Breast, Version 2.0 Device Common Name: Radiological Computer-Assisted Diagnostic Software Device Classification: 21 CFR 892.2060, Class II, POK Classification Name: Radiological Computer-Assisted Diagnostic Software (CADx) For Lesions Suspicious For Cancer Manufacturer: Koios Medical, Inc.

3. Marketed Devices

The Koios DS for Breast system is designed to assist trained interpreting physicians in analyzing the breast ultrasound images of patients with soft tissue breast lesions who have been referred for further diagnostic ultrasound examination. Ultrasound images of the breast should be acquired with a small parts linear array or dedicated breast ultrasound linear array transducers. The system provides a generated categorical output that aligns with or exceeds the sensitivity and specificity of radiologist chosen BI-RADS® categorizations using computer vision and machine learning techniques. In terms of safety and performance, this software medical device is substantially equivalent to the devices listed below:

Model: QuantX Manufacturer: Quantitative Insights, Inc. 510(k) Number: DEN170022

510(k) Summary

{4}------------------------------------------------

Model: ClearView cCAD, Version 1.0 Manufacturer: ClearView Diagnostics, Inc. 510(k) Number: K161959

4. Device Description

510(k) Summary

{5}------------------------------------------------

results are wiped from the local memory.

Koios DS for Breast is intended to be used on patients with soft tissue breast lesions who are being referred for further diagnostic ultrasound examination.

5. Indications for Use

Koios Decision Support (DS) for Breast is a software application designed to assist trained interpreting physicians in analyzing the breast ultrasound images of patients with soft tissue breast lesions who are being referred for further diagnostic ultrasound examination. Koios DS for Breast is a machine learning-based decision support system, indicated as an adjunct to diagnostic ultrasound for breast cancer. Koios DS for Breast automatically classifies user-selected region(s) of interest (ROIs) containing a breast lesion into four BI-RADSaligned categories (Benign, Probably Benign, Suspicious, Probably Malignant), and displays a continuous graphical confidence level indicator of where the lesion falls across all categories. Koios DS for Breast also automatically classifies lesion shape and orientation according to BI-RADS descriptors.

The software requires a user to select up to two ROIs, from up to two orthogonal views, that represent a single lesion to be selected and processed. When utilized by an interpreting physician who has completed the prescribed training, this device provides information that

510(k) Summary

{6}------------------------------------------------

may be useful in rendering an accurate diagnosis. Patient management decisions should not be made solely on the results of the Koios DS for Breast analysis. This device is intended to help trained interpreting physicians improve their overall accuracy as well as reduce inter- and intra-operator variability.

{7}------------------------------------------------

6. Substantial Equivalence Discussion

Product	QuantX(DEN270022)	ClearView(K161959)	cCAD Koios DS for Breast
Characteristics	CADx device used to assist in the assessment and characterization of breast abnormalities using MR image data.	Decision support device used to assist in the assessment and characterization of breast lesions using US image data.	Decision support device used to assist in the assessment and characterization of soft tissue breast lesions using US image data.
Intended Use	Diagnostic Aid using Machine Learning to characterize image features with user provided ROIs to generate a single value relative to reference abnormalities (QI Score).	Diagnostic Aid using Machine Learning to generate BI-RADS shape and orientation assessments coupled with additional user input BI-RADS descriptors to generate a preliminary BI-RADS bucket assessment.	Diagnostic Aid using Machine Learning to characterize image features with user provided ROIs to generate categorical output that aligns to BI-RADS and auto-classified shape and orientation.
TargetPopulation	High-risk screening; diagnostic workup; evaluation of known disease	Any patient that has an identified breast lesion that is referred for diagnostic ultrasound examination; excludes high-risk screening	Patients with soft tissue breast lesions who are being referred for further diagnostic ultrasound examination.
Modality Usedfor Analysis	Breast MR Data	Breast Ultrasound Data	Breast Ultrasound Data
Input	Medical images provided in a DICOM format	Medical images provided in a DICOM format	Medical images provided in a DICOM format
Output	"QI" score mapped onto histograms of distributions of malignant and benign lesions	BI-RADS bucket assessment of lesions based on auto-classified shape and orientation and user supplied inputs	Koios defined categorical and continuous outputs (confidence level indicator) that align to BI-RADS and auto-classified shape and orientation
ComparativePerformanceTesting	Metric: AUCCases: 111Readers: 19	N/A	Metric: AUCCases: 900Readers: 15
PhysicalCharacteristics	Software PackageOperates on off-the-shelf hardware	Software PackageOperates on off-the-shelf hardware	Software PackageOperates on off-the-shelf hardware
Storage	Storage not supported	Storage not supported	Storage not supported
Image Input	DICOM	DICOM	DICOM

{8}------------------------------------------------

Description of Similarities and/or Differences:

Indications for Use (IFU)

Comparing the IFU of the primary predicate device QuantX (DEN170022) and Koios DS for Breast, there are several key similarities and differences outlined below:

Both devices are intended to be utilized as diagnostic aids that operate on user-supplied Regions of Interest (ROIs). Koios DS for Breast's core classification engine does not rely on registration or segmentation to function sothese requirements are not present in its IFU as compared to those for QuantX. In the case of QuantX, the IFU states "(t)he software automatically registers images, and segments and analyzes user-selected regions of interest (ROI)." Accordingly, the IFU for Koios DS for Breast does not contain a similar provision. The IFU for Koios DS for Breast requires that a user select up to two ROIs from up to two orthogonal views that represent a single lesion to be selected and processed.

Both devices provide computer analytics based on morphological and enhancement characteristics that the QuantX device refers to as imaging (or radiomic) features that are then synthesized by an artificial intelligence algorithm into a single value. While the QuantX device generates a "QI score" which is analyzed relative to reference abnormalities, Koios DS for Breast generates a probability output that analyzes imaging features relative to a dataset of known ground truth that is then used to generate a categorical assessment. The categorical assessment provided by Koios DS for Breast aligns to BI-RADS and auto-classifies shape and orientation.

The intended use population for QuantX includes patients presenting for high-risk screening, diagnostic imaging workup, or evaluation of known disease. Koios DS for Breast is intended to be used for assisting trained interpreting physicians in analyzing patients with soft tissue breast lesions who are being referred for further diagnostic ultrasound examination. This intended use includes patients presenting with any soft tissue breast lesion through any form of imaging or physical examination resulting in a referral for diagnostic ultrasound - thus covering diagnostic imaging workup or the evaluation of known disease. Koios DS for Breast is not indicated to be used for the evaluation of patients presenting for high-risk screening, which is the only clear difference in target populations between the predicate and Koios DS for Breast.

Both the QuantX device and Koios DS for Breast are intended to be used as image viewers of multi-modality digital images including ultrasound and mammography. Both

{9}------------------------------------------------

sets of software include tools to allow users to measure and document images, and output the findings in structured DICOM formats. Neither platform is intended for primary interpretation of digital mammography images. Both platforms contain labeling instructions with a list of warnings.

The secondary predicate device, cCAD (K161959), which was also developed by Koios Medical (fka ClearView Diagnostics, Inc.), differs in that it relied upon user-supplied BI-RADS descriptors and generated a BI-RADS bucket assessment. Similar to cCAD, Koios DS for Breast automatically assesses shape and orientation for user selected ROIs, but does not support the addition of user supplied BI-RADS descriptors to suggest a BI-RADS bucket assessment. In addition, although Koios DS for Breast may be utilized as a primary diagnostic viewer for ultrasound, warnings explicitly limit users from utilizing the platform for primary interpretation of mammography images along with labeling instructions with a list of warnings, precautions and contraindications.

Modality

QuantX is intended to be utilized on breast MR data, while Koios DS for Breast is intended to be utilized on breast ultrasound data. While this clearly differentiates the products, they are both aligned to the generic FDA device type (per DEN170022) for radiological computer-assisted software (CADx) for lesions suspicious for cancer.

Koios DS for Breast shares the modality requirements of cCAD.

Input

Per the respective device descriptions of QuantX and Koios DS for Breast, the input to each consists of medical images provided in a DICOM format. While there are modality differences that are addressed above, the technical implementation for ingesting images for processing occurs via the same DICOM based interface.

Koios DS for Breast shares the input requirements of ClearView Diagnostics' cCAD product.

Output

The output of both systems differs in both information and style of display. The QuantX system outputs a "QI" score that is then mapped onto distributions of malignant and benign lesions. It does not explicitly compute a likelihood of malignancy, but instead relies on the user to interpret the QI score and its respective position in the benign/malignant histograms to impact their assessment of the lesion's underlying risk. Conversely, Koios DS for Breast directly characterizes a lesion based on categorical and continuous outputs (confidence level

510(k) Summary

{10}------------------------------------------------

indicator) that are aligned to BI-RADS and auto-classifies shape and orientation. This allows for users to interpret the automated assessment alongside an existing risk stratification and feature description lexicon.

In addition, Koios DS for Breast implements an automated assessment of shape and orientation as done by cCAD. The results are presented in a form substantially similar to the form provided by cCAD.

Koios DS for Breast, does not provide a BI-RADS bucket assessment of lesions as cCAD does. Instead, Koios DS for Breast aligns its risk assessment to BI-RADS with categories chosen such that they align with or exceed the sensitivity and specificity of BI-RADS categorizations.

Algorithm

Koios DS for Breast and cCAD share a similar algorithm set, training data, and validation approach for automated shape and orientation assessment.

While Koios DS for Breast and QuantX both aim to characterize lesions suspicious for cancer, their respective differences in modality necessitate differences in the algorithmic approach applied. Due to the fact that QuantX does not disclose their algorithmic approach, Koios Medical cannot speculate as to the underlying architecture of their system. Instead, Koios Medical aims to demonstrate equivalence through performance impact.

Performance Testing

Koios DS for Breast and cCAD share a similar algorithm set, training data, and validation approach for automated shape and orientation assessment. As such their performance results are directly comparable.

When comparing clinical validation between Koios DS for Breast and QuantX, the sponsors used similar endpoints in their clinical studies. Both sponsors evaluated an Area Under the Curve (AUC) shift when comparing the performance of users alone versus users utilizing the respective software platform. The number of cases evaluated in the QuantX study was 111, while the Koios DS for Breast study evaluated a total of 900 cases. The number of readers utilized in the QuantX study was 19, while the Koios DS for Breast study used a total of 15 readers.

While the results of QuantX study showed a mean AUC shift of +0.0487, the Koios DS for Breast study showed a mean shift of +0.037. The 95% CI was noticeably tighter for the AUC with a standard error of .0036 for Koios DS for Breast compared to .0254 when computing the MRMC estimated AUC via the trapezoidal rule. Further, the AUC of both

{11}------------------------------------------------

the first and second reads is considerably higher in the Koios DS for Breast study set than in the QuantX study with an AUC shift of .7090 to .7577 for QuantX and a shift from .836 to .873 for Koios DS for Breast. While the absolute values for AUC may differ based on reader, data, and modality; the range for possible improvement has a smaller lower bound in the Koios DS for Breast clinical evaluation. In conclusion, the Koios DS for Breast study has demonstrated substantially equivalent performance to QuantX by showing a statistically significant acceptance of similar success criteria to QuantX with a smaller standard error.

7. Clinical Performance Data

A clinical study was executed to determine the effect of Koios DS for Breast on reader performance. The study objective was to determine the impact on Interpreting Physician (Reader) performance as defined by the area under the Receiver Operating Characteristic (ROC) Curve (AUC) when Koios DS for Breast and an ultrasound examination are combined (USE + DS), compared to USE Alone in patients that present with a soft tissue breast lesion through any form of imaging or physical examination and are referred for diagnostic ultrasound.

The study consisted of 15 readers with varying levels of training and experience providing analysis on a randomized set of 900 patient cases presented with USE + DS and USE Alone in two reading periods separated by a 1-month wash-out, totaling 1800 cases analyzed per reader. The reader set and dataset were distributed in accordance with FDA guidance and are explained in detail below:

Reader Experience

{12}------------------------------------------------

Reader ID	BoardCertification/Specialty	Breast FellowshipTrained and/orDedicated BreastImager	Years ofExperience -Mammographyand/or BreastUltrasound	Academic InstitutionAffiliation (Yes/No)	MQSAQualifiedInterpretingPhysician
1	Diagnostic Radiology	No	13 Years	No	Yes
2	Diagnostic Radiology	No	4 Years	No	No
3	Diagnostic Radiology	Yes	7 Years	Yes	Yes
4	Breast Surgeon	No	0 Years	No	No
5	OB/GYN	No	20 Years	No	No
6	Diagnostic Radiology	No	13 Years	Yes	No
7	Diagnostic Radiology	No	3 Years	Yes	No
8	OB/GYN	No	0 Years	No	No
9	Diagnostic Radiology	Yes	15 Years	No	Yes
10	Diagnostic Radiology	No	13 Years	No	No
11	Diagnostic Radiology	Yes	30 Years	No	Yes
12	Diagnostic Radiology	Yes	10 Years	Yes	Yes
13	Diagnostic Radiology	No	0 Years	No	No
14	Interventional Radiology	No	4 Years	No	No
15	Breast Surgeon	No	25 Years	Yes	No

Reader Experience Breakdown

{13}------------------------------------------------

Dataset Demographic Information

The following patient demographics, as measured by the Breast Cancer Surveillance Consortium (2006-2009), were met to ensure populations representative of national rates:

592 White women 73 Hispanic women 77 African American women 133 Asian women 25 cases that do not fall in the above categories

The age distribution of patients included within the study were:

• <40:	15.3%	= 138
• 40-49:	25.3%	= 228
• 50-59:	23.0%	= 207
• 60-74:	26.1%	= 235
• 75-84:	7.6%	= 68
• 85+:	1.0%	= 9
• N/A:	1.7%	= 15

Breast Density information for the clinical study was as follows:

. BI-RADS 1: 12.8%
. BI-RADS 2: 38.1%
BI-RADS 3: 33.2% .
. BI-RADS 4: 15.9%

The lesion sizes included within the study ranged from 3-80mm with 332/900 (36.9%) <10mm, 229/900 (25.4%) 10-14mm, 132/900 (14.7% 15-19mm, and 200/900 (22.2%) > 20mm. Size was unavailable for 7 lesions (0.8%). The minimum lesion size was 3mm.

Per the primary endpoint of the study, ROC curves were generated and analyzed. All AUCs were computed via the trapezoidal approximation. Based on the standard error measurements, the error can be propagated to estimate the mean performance interface and 95% confidence interval. This was found to be 0.0370 (0.030, 0.044) at a = .05, satisfying the success criteria for the primary endpoint.

To characterize the effect of Koios DS (USE + DS) system on inter-operator variability, the Kendall Tau-B correlation coefficient was computed in a pairwise manner for all readers. The metric is > 0 for all reader pairs. The standard error for USE + DS and USE Alone was computed to assess if the shifts in the metric were significant. The average Kendall Tau-B of USE Alone was .5404 (.5301, .5507) and the average Kendall Tau-B of

{14}------------------------------------------------

USE + DS was .6797 (.6653, .6941) with 95% CI demonstrating a significant increase in the metric (α = . 05).

Also assessed was the effect of Koios DS on intra-operator variability leveraging 150 reads that did not switch from USE Alone to USE + DS across the washout session in the reader study (75 each). USE Alone class switching rate was 13.6% and the USE + DS class switching rate was 10.8% (p = 0.042), demonstrating a statistically significant reduction in intra-reader variability when using USE + DS.

8. Non-Clinical Performance Data

Malignancy Risk Classification:

Bench testing was performed to ascertain the degree of concordance with trained interpreting physicians. Ground truth for malignancy risk classification was determined by pathology or 1-year follow-up for cases that were not biopsied. The system was analyzed on 900 lesions from 900 different patients set aside from the system's training data for the purpose of validating performance. Each lesion is represented by two orthogonal images (e.g. radial and anti-radial), providing a total of 1800 images. System performance on the 900 cases reported an AUC of 88.2%.

BI-RADS Descriptors:

Bench testing was performed to ascertain the degree of concordance with trained interpreting physicians. Ground truth for shape and orientation was supplied by three MQSA certified radiologists. These physicians, all with over 20 years of experience and at least 3000 images read per year, evaluated this dataset on the aforementioned parameters. The system was used to analyze these 1300 cases on the same parameters. In the first test, the system was analyzed on 1204 cases which had a majority decision on shape and 1227 lesions which had a majority decision on orientation. The Koios DS for Breast system was able to achieve overall accuracy that fell within the 95% confidence interval of the radiologists' performance, rendering them statistically equivalent.

{15}------------------------------------------------

Category	Koios DSfor BreastproperlyIdentified	Koios DS forBreastProportion	95% Cl	Cut Off forProportion Pointestimate	Conclusion
Lesionorientation	1125	91.12%	[89.43%92.60%]	86.12%	Within criteria establishedfor clinical equivalence
Lesion shape	1066	87.62%	[85.68%89.36%]	83.54%	Within criteria establishedfor clinical equivalence

Koios DS performance for shape and orientation classification, when measured against majority decision

In the second test, categorical agreement between each pair of readers was compared to agreement between each reader and the system. For this test, majority agreement was not enforced and all cases were analyzed for reader and reader-system agreement. Agreement was estimated by means of calculating the Cohen's Kappa coefficient for each pair. On average, for both shape and orientation, the level of agreement between two pairs of readers was not found to statistically differ from the level of agreement between readers and the system.

	к: Reader vs Reader	к: System vs Reader
Shape	0.769 [0.711, 0.826]	0.738 [0.679, 0.797]
Orientation	0.728 [0.655, 0.801]	0.744 [0.675, 0.813]

Average kappa coefficient and 95% confidence intervals for reader and system vs reader categorizations

{16}------------------------------------------------

9. Conclusion

Based on the substantial equivalence evaluation, which is derived from the nonclinical and clinical tests that demonstrate that the device is as safe, as effective, and performs as well as or better than the legally marketed device predicates, we have determined that the Koios DS for Breast product is substantially equivalent to DEN170022 and K161959.

Regulation Number and Section

§ 892.2060 Radiological computer-assisted diagnostic software for lesions suspicious of cancer.

(a)
Identification. A radiological computer-assisted diagnostic software for lesions suspicious of cancer is an image processing prescription device intended to aid in the characterization of lesions as suspicious for cancer identified on acquired medical images such as magnetic resonance, mammography, radiography, or computed tomography. The device characterizes lesions based on features or information extracted from the images and provides information about the lesion(s) to the user. Diagnostic and patient management decisions are made by the clinical user.(b)
Classification. Class II (special controls). The special controls for this device are:(1) Design verification and validation must include:
(i) A detailed description of the image analysis algorithms including, but not limited to, a detailed description of the algorithm inputs and outputs, each major component or block, and algorithm limitations.
(ii) A detailed description of pre-specified performance testing protocols and dataset(s) used to assess whether the device will improve reader performance as intended.
(iii) Results from performance testing protocols that demonstrate that the device improves reader performance in the intended use population when used in accordance with the instructions for use. The performance assessment must be based on appropriate diagnostic accuracy measures (
e.g., receiver operator characteristic plot, sensitivity, specificity, predictive value, and diagnostic likelihood ratio). The test dataset must contain sufficient numbers of cases from important cohorts (e.g., subsets defined by clinically relevant confounders, effect modifiers, concomitant diseases, and subsets defined by image acquisition characteristics) such that the performance estimates and confidence intervals of the device for these individual subsets can be characterized for the intended use population and imaging equipment.(iv) Standalone performance testing protocols and results of the device.
(v) Appropriate software documentation (
e.g., device hazard analysis; software requirements specification document; software design specification document; traceability analysis; and description of verification and validation activities including system level test protocol, pass/fail criteria, results, and cybersecurity).(2) Labeling must include:
(i) A detailed description of the patient population for which the device is indicated for use.
(ii) A detailed description of the intended reading protocol.
(iii) A detailed description of the intended user and recommended user training.
(iv) A detailed description of the device inputs and outputs.
(v) A detailed description of compatible imaging hardware and imaging protocols.
(vi) Warnings, precautions, and limitations, including situations in which the device may fail or may not operate at its expected performance level (
e.g., poor image quality or for certain subpopulations), as applicable.(vii) Detailed instructions for use.
(viii) A detailed summary of the performance testing, including: Test methods, dataset characteristics, results, and a summary of sub-analyses on case distributions stratified by relevant confounders (
e.g., lesion and organ characteristics, disease stages, and imaging equipment).